Thimaporn Phetkaew
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Thimaporn Phetkaew has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Wattanapong Kurdthongmee
School of Engineering and Technology, Walailak University, Nakhon Si Thammarat 80160
4 shared publications - Wei-Jou Duh
AI Research Center (AINTU), National Taiwan University, Taipei, Taiwan
2 shared publications - Anurak Thungtong
Walailak University
1 shared publication - Boonserm Kijsirikul
Chulalongkorn University
1 shared publication - Chirawat Wattanapanich
Walailak University
1 shared publication Karanrat Thammarak
1 shared publication
Latest Publications
- Open Access
- 7 September 2026
- Published by Elsevier in SSRN Electronic Journal
When Is a Corrupted Calibration Label Detectable?A Model-Relative Detectability Floor for Few-Shot Gaze Personalization
Few-shot gaze personalization involves adapting a pretrained estimator to a new user using a limited number of calibration frames, with the assumption that each frame accurately captures the user looking at a known target. While image corruption that violates this assumption can be identified from the pixels, an attention lapse cannot, as it results in a clean image paired with an incorrect gaze label. Label noise has been extensively studied at the scale of training sets, where population statistics are available, and in few-shot classification, where prototypes exist; however, few-shot regression lacks both. We investigate the detectability of a corrupted calibration label from nine frames. By scoring each frame based on the personalized model's prediction residual, we locate a detectability floor: an ROC-AUC of 0.7 is achieved at a label displacement of δ = 4.2–4.8° against a personalized error of 3.57°, which remains stable across support-set contamination ranging from 10% to 40%. This floor is model-relative, with the crossing correlating with a subject's own error at r = +0.79, allowing the floor of a model with known accuracy to be anticipated rather than remeasured. Compared to five baselines, the separation is determined by mechanism rather than provenance: population-statistical scorers offer no advantage at nine frames, while per-frame residuals transfer intact, including the small-loss criterion that prior work explicitly excludes. We recommend using the one-adaptation resubstitution residual at a threshold of 3.42°, which recovers 1.3 corrupted frames per nine-frame session while incorrectly flagging 0.5 clean ones. Under a structured model of attention lapse, 8–10% of corruptions fall below the floor and are inherently undetectable, increasing to 16% for the most affected subject. Decomposing the damage a corrupted frame does, we find that label corruption exceeds frame loss only above the floor, while image corruption never does.
- 7 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessWhen Is a Corrupted Calibration Label Detectable?A Model-Relative Detectability Floor for Few-Shot Gaze Personalization
Few-shot gaze personalization involves adapting a pretrained estimator to a new user using a limited number of calibration frames, with the assumption that each frame accurately captures the user looking at a known target. While image corruption that violates this assumption can be identified from the pixels, an attention lapse cannot, as it results in a clean image paired with an incorrect gaze label. Label noise has been extensively studied at the scale of training sets, where population statistics are available, and in few-shot classification, where prototypes exist; however, few-shot regression lacks both. We investigate the detectability of a corrupted calibration label from nine frames. By scoring each frame based on the personalized model's prediction residual, we locate a detectability floor: an ROC-AUC of 0.7 is achieved at a label displacement of δ = 4.2–4.8° against a personalized error of 3.57°, which remains stable across support-set contamination ranging from 10% to 40%. This floor is model-relative, with the crossing correlating with a subject's own error at r = +0.79, allowing the floor of a model with known accuracy to be anticipated rather than remeasured. Compared to five baselines, the separation is determined by mechanism rather than provenance: population-statistical scorers offer no advantage at nine frames, while per-frame residuals transfer intact, including the small-loss criterion that prior work explicitly excludes. We recommend using the one-adaptation resubstitution residual at a threshold of 3.42°, which recovers 1.3 corrupted frames per nine-frame session while incorrectly flagging 0.5 clean ones. Under a structured model of attention lapse, 8–10% of corruptions fall below the floor and are inherently undetectable, increasing to 16% for the most affected subject. Decomposing the damage a corrupted frame does, we find that label corruption exceeds frame loss only above the floor, while image corruption never does.
- Open Access
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 71762-71775
A Calibration-Free Multi-Expert System for Automated Diopter Measurement: Overcoming Noise-Induced Binocular Inconsistency
Estimating ocular alignment in unconstrained settings faces challenges due to Noise-Induced Binocular Inconsistency (NIBI) which results from random events like blinking, head motion and tracking noise leading to temporary inter-ocular inconsistencies. Existing solutions typically follow either a framebased or a classification-based pipeline which often fail to yield reliable results especially when required to produce continuous measurements for clinical interpretation. In this work, we introduce a calibration-free deep multi-expert architecture that is capable of estimating the required prism diopters in a matter of seconds, by analyzing a short monocular video clip in real-time. Unlike prior methods, we tackle ocular alignment as a temporal problem, which results in improved robustness. Our approach consists of a Geometric Expert (Living Ruler) which outputs iris-normalized and scale invariant features. These are followed by a Trajectory Expert that encodes both eye movement temporal dynamics and deep image features, which are then passed through a Stability Supervisor. The Supervisor — a fully convolutional Transformer encoder — outputs frame-wise reliability scores which are subsequently used to suppress any noise-induced inconsistencies. Due to the lack of publicly available datasets with corresponding prism diopter annotations, we simulate geometry-based reference deviation values for eyes with real human eye geometry from the Columbia Gaze Dataset. Experimental results demonstrate that the proposed method outperforms other solutions in terms of both accuracy (MAE) of 1.3038Δ and R2 of 0.9963 for the range 0–50Δ and stability where a temporal fusion strategy leads to better results compared to frame-wise approaches especially when affected by transient noise. These findings indicate that continuous, calibration-free estimation of ocular deviation from standard video input is feasible, supporting potential applications in tele-screening and longitudinal monitoring.
- 11 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 71762-71775
Open AccessA Calibration-Free Multi-Expert System for Automated Diopter Measurement: Overcoming Noise-Induced Binocular Inconsistency
Estimating ocular alignment in unconstrained settings faces challenges due to Noise-Induced Binocular Inconsistency (NIBI) which results from random events like blinking, head motion and tracking noise leading to temporary inter-ocular inconsistencies. Existing solutions typically follow either a framebased or a classification-based pipeline which often fail to yield reliable results especially when required to produce continuous measurements for clinical interpretation. In this work, we introduce a calibration-free deep multi-expert architecture that is capable of estimating the required prism diopters in a matter of seconds, by analyzing a short monocular video clip in real-time. Unlike prior methods, we tackle ocular alignment as a temporal problem, which results in improved robustness. Our approach consists of a Geometric Expert (Living Ruler) which outputs iris-normalized and scale invariant features. These are followed by a Trajectory Expert that encodes both eye movement temporal dynamics and deep image features, which are then passed through a Stability Supervisor. The Supervisor — a fully convolutional Transformer encoder — outputs frame-wise reliability scores which are subsequently used to suppress any noise-induced inconsistencies. Due to the lack of publicly available datasets with corresponding prism diopter annotations, we simulate geometry-based reference deviation values for eyes with real human eye geometry from the Columbia Gaze Dataset. Experimental results demonstrate that the proposed method outperforms other solutions in terms of both accuracy (MAE) of 1.3038Δ and R2 of 0.9963 for the range 0–50Δ and stability where a temporal fusion strategy leads to better results compared to frame-wise approaches especially when affected by transient noise. These findings indicate that continuous, calibration-free estimation of ocular deviation from standard video input is feasible, supporting potential applications in tele-screening and longitudinal monitoring.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Photometric Domain Randomization for Robust Iris-Center Localization Across Capture Conditions
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Open AccessPhotometric Domain Randomization for Robust Iris-Center Localization Across Capture Conditions
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 138395-138419
Dynamic Adapter Placement for Robust Few-Shot Gaze Personalization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 138395-138419
Open AccessDynamic Adapter Placement for Robust Few-Shot Gaze Personalization
- 13 March 2024
- Published by Springer Nature in European Journal of Wood and Wood Products
- Vol. 82 (4) , 1061-1068
Using machine learning as an adaptive controller framework for optimizing properties of particleboard
- 13 March 2024
- Published by Springer Nature in European Journal of Wood and Wood Products
- Vol. 82 (4) , 1061-1068
Using machine learning as an adaptive controller framework for optimizing properties of particleboard
- Open Access
- 1 July 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 3519-3525
Sub-classifier construction for error correcting output code using minimum weight perfect matching
Multi-class classification is mandatory for real world problems and one of promising techniques for multi-class classification is Error Correcting Output Code. We propose a method for constructing the Error Correcting Output Code to obtain the suitable combination of positive and negative classes encoded to represent binary classifiers. The minimum weight perfect matching algorithm is applied to find the optimal pairs of subset of classes by using the generalization performance as a weighting criterion. Based on our method, each subset of classes with positive and negative labels is appropriately combined for learning the binary classifiers. Experimental results show that our technique gives significantly higher performance compared to traditional methods including One-Versus-AU, the dense random code, and the sparse random code. Moreover, our method requires significantly smaller number of binary classifiers while maintaining accuracy compared to One-Versus-One.
- 1 July 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 3519-3525
Open AccessSub-classifier construction for error correcting output code using minimum weight perfect matching
Multi-class classification is mandatory for real world problems and one of promising techniques for multi-class classification is Error Correcting Output Code. We propose a method for constructing the Error Correcting Output Code to obtain the suitable combination of positive and negative classes encoded to represent binary classifiers. The minimum weight perfect matching algorithm is applied to find the optimal pairs of subset of classes by using the generalization performance as a weighting criterion. Based on our method, each subset of classes with positive and negative labels is appropriately combined for learning the binary classifiers. Experimental results show that our technique gives significantly higher performance compared to traditional methods including One-Versus-AU, the dense random code, and the sparse random code. Moreover, our method requires significantly smaller number of binary classifiers while maintaining accuracy compared to One-Versus-One.